© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14806
    Prev
    Next
    INDEX
    Explanations

    halve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ṃ
    -0.56
    ardless
    -0.52
    IconModule
    -0.50
    });*/
    -0.48
    onHide
    -0.47
    Comté
    -0.47
    sedown
    -0.47
    WireFormat
    -0.47
    ]";
    -0.47
     minimization
    -0.46
    POSITIVE LOGITS
     دیکھیے
    0.69
     ModelExpression
    0.68
    orianCalendar
    0.66
     the
    0.59
     Italijani
    0.58
     Normdatei
    0.58
     <=",
    0.57
    MLLoader
    0.56
    EndInit
    0.54
     préfère
    0.53
    Activations Density 0.004%

    No Known Activations